【记录】win10平台6G显存运行Qwen-1.8B

Last updated on January 5, 2024 pm

Llama.cpp 能 CPU & GPU 环境混合推理,这里记录一下在 windows10 平台上运行 Qwen-1.8B 的过程,显卡是 1660Ti 。

准备模型

1
2
3
4
5
6
7
conda create -n llamaConvert python=3.10 git -c conda-forge
conda activate llamaConvert
cd D:\llama
git clone --depth=1 https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
python -m pip install -r requirements.txt
pip install tiktoken
1
2
3
4
python -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='Qwen/Qwen-1_8B-Chat', local_dir=r'D:\qwen', ignore_patterns=['*.h5', '*.ot', '*.msgpack', '*.safetensors'])"
cd D:\qwen
D:\aria2\aria2c.exe --all-proxy='http://127.0.0.1:7890' -o 'model-00001-of-00002.safetensors' "https://huggingface.co/Qwen/Qwen-1_8B-Chat/resolve/main/model-00001-of-00002.safetensors?download=true"
D:\aria2\aria2c.exe --all-proxy='http://127.0.0.1:7890' -o 'model-00002-of-00002.safetensors' "https://huggingface.co/Qwen/Qwen-1_8B-Chat/resolve/main/model-00002-of-00002.safetensors?download=true"
1
2
3
cd D:\llama\llama.cpp
python convert-hf-to-gguf.py D:\qwen
# Model successfully exported to 'D:\qwen\ggml-model-f16.gguf'

运行模型

1
2
3
4
5
6
conda create -n llamaCpp libcublas cuda-toolkit git -c nvidia -c conda-forge
conda activate llamaCpp
cd D:\llama ; .\main.exe ## 检查能否正确运行
cd D:\llama ; .\quantize.exe --help ## 自己决定量化方式
.\quantize.exe D:\qwen\ggml-model-f16.gguf .\qwen-1_8-f16.gguf COPY
.\server.exe -m .\qwen-1_8-f16.gguf -c 4096 --n-gpu-layers 50 ## 调节 n-gpu-layers 平衡 CPU & GPU
  • 访问 http://127.0.0.1:8080 选择 Completion 进行测试

微调模型

附加 Yi-6B-Chat

Yi-6B是零一万物开源的双语语言模型,经过3T多语种语料库的训练,在语言理解、常识推理、阅读理解等方面有一定潜力。

1
2
3
4
5
6
cd D:\models\01yi
D:\aria2\aria2c.exe --all-proxy='http://127.0.0.1:7890' -o 'model-00001-of-00003.safetensors' "https://huggingface.co/01-ai/Yi-6B-Chat/resolve/main/model-00001-of-00003.safetensors?download=true"
D:\aria2\aria2c.exe --all-proxy='http://127.0.0.1:7890' -o 'model-00002-of-00003.safetensors' "https://huggingface.co/01-ai/Yi-6B-Chat/resolve/main/model-00002-of-00003.safetensors?download=true"
D:\aria2\aria2c.exe --all-proxy='http://127.0.0.1:7890' -o 'model-00003-of-00003.safetensors' https://huggingface.co/01-ai/Yi-6B-Chat/resolve/main/model-00003-of-00003.safetensors?download=true
conda activate llamaConvert
python -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='01-ai/Yi-6B-Chat', local_dir=r'D:\models\01yi', ignore_patterns=['*.h5', '*.ot', '*.msgpack', '*.safetensors'])"
1
2
3
4
5
6
7
8
conda activate llamaConvert
cd D:\llama\llama.cpp
python convert.py D:\models\01yi
# Wrote D:\models\01yi\ggml-model-f16.gguf
conda activate llamaCpp
cd D:\llama ; .\quantize.exe --help
.\quantize.exe D:\models\01yi\ggml-model-f16.gguf .\01yi-6b-Q4_K_M.gguf Q4_K_M
.\server.exe -m .\01yi-6b-Q4_K_M.gguf -c 4096 --n-gpu-layers 50

附加 百川2

1
2
3
4
5
6
7
8
9
10
11
cd D:\models\baichuan
D:\aria2\aria2c.exe --all-proxy='http://127.0.0.1:7890' -o 'pytorch_model.bin' "https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat/resolve/main/pytorch_model.bin?download=true"
conda activate llamaConvert
python -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='baichuan-inc/Baichuan2-7B-Chat', local_dir=r'D:\models\baichuan', ignore_patterns=['*.h5', '*.bin', '*.ot', '*.msgpack', '*.safetensors'])"
cd D:\llama\llama.cpp
python convert.py D:\models\baichuan
# Wrote D:\models\baichuan\ggml-model-f16.gguf
conda activate llamaCpp
cd D:\llama ; .\quantize.exe --help
.\quantize.exe D:\models\baichuan\ggml-model-f16.gguf .\baichuan-7b-Q3_K_M.gguf Q3_K_M
.\server.exe -m .\baichuan-7b-Q3_K_M.gguf -c 2048 --n-gpu-layers 30

附加 tigerbot-13b

tigerbot-13bchinese-llm-benchmark 上排名靠前。

1
2
3
4
5
6
7
8
9
10
11
cd D:\models\tigerbot
D:\aria2\aria2c.exe --all-proxy='http://127.0.0.1:7890' -o 'pytorch_model-00001-of-00003.bin' --max-download-limit=6M "https://huggingface.co/TigerResearch/tigerbot-13b-chat-v5/resolve/main/pytorch_model-00001-of-00003.bin?download=true"
D:\aria2\aria2c.exe --all-proxy='http://127.0.0.1:7890' -o 'pytorch_model-00002-of-00003.bin' --max-download-limit=6M "https://huggingface.co/TigerResearch/tigerbot-13b-chat-v5/resolve/main/pytorch_model-00002-of-00003.bin?download=true"
D:\aria2\aria2c.exe --all-proxy='http://127.0.0.1:7890' -o 'pytorch_model-00003-of-00003.bin' --max-download-limit=6M "https://huggingface.co/TigerResearch/tigerbot-13b-chat-v5/resolve/main/pytorch_model-00003-of-00003.bin?download=true"
conda activate llamaConvert
python -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='TigerResearch/tigerbot-13b-chat-v5', local_dir=r'D:\models\tigerbot', ignore_patterns=['*.h5', '*.bin', '*.ot', '*.msgpack', '*.safetensors'])"
cd D:\llama\llama.cpp
python convert.py D:\models\tigerbot --padvocab
cd D:\llama ; .\quantize.exe --help
.\quantize.exe D:\models\tigerbot\ggml-model-f16.gguf D:\models\tigerbot-13B-Chat-Q4_K_M.gguf Q4_K_M
.\server.exe -m D:\models\tigerbot-13B-Chat-Q4_K_M.gguf -c 4096

感觉 6G 显存下,比较好用的是 Yi-6B-Chat-Q4_K_M
tigerbot-13b 在 R5 5600H 上推理速度 4.6 tokens/s,CPU 使用率 60%,频率 3.5GHz,应该是内存带宽瓶颈


【记录】win10平台6G显存运行Qwen-1.8B
https://hexo.limour.top/Running-Qwen-on-the-Win10-platform-with-6GB-of-video-memory
Author
Limour
Posted on
January 1, 2024
Updated on
January 5, 2024
Licensed under